Decentralized Flood Forecasting Using Deep Neural Networks
This addresses flood forecasting for emergency management, but appears incremental as it builds on existing methods with neural networks.
The study tackled flood prediction by exploring deep neural networks for forecasting stream stages, showing they can be helpful in time-series forecasting and support improving existing models through data assimilation.
Predicting flood for any location at times of extreme storms is a longstanding problem that has utmost importance in emergency management. Conventional methods that aim to predict water levels in streams use advanced hydrological models still lack of giving accurate forecasts everywhere. This study aims to explore artificial deep neural networks' performance on flood prediction. While providing models that can be used in forecasting stream stage, this paper presents a dataset that focuses on the connectivity of data points on river networks. It also shows that neural networks can be very helpful in time-series forecasting as in flood events, and support improving existing models through data assimilation.